chore: align bridge with CommandCode 0.26.8

Author: yelixir-dev

.env.example

@@ -15,7 +15,7 @@ COMMANDCODE_API_BASE=https://api.commandcode.ai
 COMMANDCODE_DEFAULT_MODEL=deepseek/deepseek-v4-pro
 COMMANDCODE_ALLOWED_MODELS=deepseek/deepseek-v4-pro,deepseek/deepseek-v4-flash
 COMMANDCODE_ALLOW_UNKNOWN_MODELS=false
-COMMANDCODE_CLI_VERSION=0.26.7
+COMMANDCODE_CLI_VERSION=0.26.8
 COMMANDCODE_TIMEOUT_MS=300000
 COMMANDCODE_EMPTY_VISIBLE_RESPONSE_POLICY=error_on_length
 

README.ko.md

@@ -30,18 +30,18 @@ CommandCode Bridge는 CommandCode 계정을 OpenAI-compatible HTTP API로 노출
 
 ## 버전
 
-현재 bridge version: **v0.26.7**.
+현재 bridge version: **v0.26.8**.
 
 버전은 `/health` 응답과 웹 대시보드 오른쪽 위에 표시됩니다.
 
-### v0.26.7 CommandCode 호환성 업데이트
+### v0.26.8 CommandCode 호환성 업데이트
 
-이번 bridge release는 공식 `command-code` npm package `0.26.7`에 맞췄습니다.
+이번 bridge release는 공식 `command-code` npm package `0.26.8`에 맞췄습니다.
 
-- 기본 upstream `x-command-code-version` header는 `COMMANDCODE_CLI_VERSION`으로 덮어쓰지 않는 한 `0.26.7`을 보냅니다.
-- bridge package/runtime version도 `0.26.7`이라 `/health`, dashboard, npm metadata가 대상 CommandCode CLI version과 일치합니다.
-- `command-code@0.26.7` bundle을 직접 확인한 결과 bridge 핵심 API path(`/alpha/generate`, `/alpha/whoami`, `/alpha/billing/credits`, `/alpha/billing/subscriptions`, `/alpha/usage/summary`)는 기존 bridge 경로와 호환됩니다.
-- model catalog를 `0.26.7` CLI bundle 기준으로 갱신했습니다. 기존 enabled default는 보수적으로 유지하고, Qwen 3.6 Max Preview, MiniMax M2.5, Kimi K2.5, GLM-5, GPT 5.4/5.3 Codex/5.4 Mini, 구 Claude variant 등 추가 발견 모델은 operator가 켤 때까지 disabled 상태로 포함했습니다.
+- 기본 upstream `x-command-code-version` header는 `COMMANDCODE_CLI_VERSION`으로 덮어쓰지 않는 한 `0.26.8`을 보냅니다.
+- bridge package/runtime version도 `0.26.8`이라 `/health`, dashboard, npm metadata가 대상 CommandCode CLI version과 일치합니다.
+- `command-code@0.26.8` bundle을 직접 확인한 결과 bridge 핵심 API path(`/alpha/generate`, `/alpha/whoami`, `/alpha/billing/credits`, `/alpha/billing/subscriptions`, `/alpha/usage/summary`)는 기존 bridge 경로와 호환됩니다.
+- model catalog를 `0.26.8` CLI bundle 기준으로 갱신했습니다. 기존 enabled default는 보수적으로 유지하고, Qwen 3.6 Max Preview, MiniMax M2.5, Kimi K2.5, Step 3.5 Flash, Gemini 3.1 Flash Lite, GLM-5, GPT 5.4/5.3 Codex/5.4 Mini, 구 Claude variant 등 추가 발견 모델은 operator가 켤 때까지 disabled 상태로 포함했습니다.
 
 ## 구조
 
@@ -247,6 +247,8 @@ curl -N http://127.0.0.1:9992/v1/chat/completions \
 npm run smoke
 ```
 
+smoke script는 `.env`를 읽은 뒤 installed-service env file(`~/.config/commandcode-bridge/env`, Yorha macOS bridge host에서는 `/Users/yorha/.config/commandcode-bridge/env`)을 읽고, 마지막으로 shell에서 직접 지정한 값을 우선합니다. 다른 설치본을 검증할 때는 `BRIDGE_ENV_FILE=/path/to/env`를 지정하십시오. `BRIDGE_BASE_URL`, `BRIDGE_API_KEY` 같은 shell 값이 항상 파일 값보다 우선합니다.
+
 계정은 도달 가능하지만 balance/credit 때문에 일시적으로 generation이 막힌 경우 routing-only fail-closed smoke mode를 사용할 수 있습니다.
 
 ```bash
@@ -275,7 +277,7 @@ http://<host-or-tailnet-ip>:9992/dashboard
 
 - **Header**
   - bridge online/offline 상태 표시.
-  - `v0.26.7` 같은 bridge version 표시.
+  - `v0.26.8` 같은 bridge version 표시.
 - **Server Bind**
   - local-only면 `127.0.0.1`.
   - LAN/Tailscale/VPN/reverse proxy 뒤에서만 `0.0.0.0`.
@@ -487,7 +489,7 @@ x-api-key: <BRIDGE_API_KEY>
 | `COMMANDCODE_DEFAULT_MODEL`                  | `deepseek/deepseek-v4-pro`   | `default`가 사용할 model.                                                                                  |
 | `COMMANDCODE_ALLOWED_MODELS`                 | Pro + Flash/catalog defaults | comma-separated allowlist.                                                                                 |
 | `COMMANDCODE_ALLOW_UNKNOWN_MODELS`           | `false`                      | 임의 model ID를 upstream으로 통과. 운영 비권장.                                                            |
-| `COMMANDCODE_CLI_VERSION`                    | `0.26.7`                     | upstream으로 보내는 version header.                                                                        |
+| `COMMANDCODE_CLI_VERSION`                    | `0.26.8`                     | upstream으로 보내는 version header.                                                                        |
 | `COMMANDCODE_TIMEOUT_MS`                     | `300000`                     | upstream request timeout.                                                                                  |
 | `COMMANDCODE_EMPTY_VISIBLE_RESPONSE_POLICY`  | `error_on_length`            | empty visible `finish_reason: length`를 fail-closed. `allow`는 legacy blank success 유지.                  |
 | `REQUEST_BODY_LIMIT_BYTES`                   | `1048576`                    | Fastify body limit.                                                                                        |

README.md

@@ -30,18 +30,18 @@ CommandCode Bridge is a trusted-environment HTTP bridge that exposes a small Ope
 
 ## Version
 
-Current bridge version: **v0.26.7**.
+Current bridge version: **v0.26.8**.
 
 The version is also returned from `/health` and shown in the top-right of the web dashboard.
 
-### v0.26.7 CommandCode compatibility update
+### v0.26.8 CommandCode compatibility update
 
-This bridge release is aligned with the official `command-code` npm package `0.26.7`:
+This bridge release is aligned with the official `command-code` npm package `0.26.8`:
 
-- The default upstream `x-command-code-version` header now advertises `0.26.7` unless `COMMANDCODE_CLI_VERSION` overrides it.
-- The bridge package/runtime version is also `0.26.7` so `/health`, the dashboard, and the npm metadata match the CommandCode CLI version being targeted.
-- Direct inspection of the `command-code@0.26.7` bundle confirmed that the bridge-critical API paths remain compatible: `/alpha/generate`, `/alpha/whoami`, `/alpha/billing/credits`, `/alpha/billing/subscriptions`, and `/alpha/usage/summary`.
-- The model catalog was refreshed from the `0.26.7` CLI bundle. Existing enabled defaults stay conservative, while additional discovered entries such as Qwen 3.6 Max Preview, MiniMax M2.5, Kimi K2.5, GLM-5, GPT 5.4/5.3 Codex/5.4 Mini, and older Claude variants are present but disabled by default until an operator enables them.
+- The default upstream `x-command-code-version` header now advertises `0.26.8` unless `COMMANDCODE_CLI_VERSION` overrides it.
+- The bridge package/runtime version is also `0.26.8` so `/health`, the dashboard, and the npm metadata match the CommandCode CLI version being targeted.
+- Direct inspection of the `command-code@0.26.8` bundle confirmed that the bridge-critical API paths remain compatible: `/alpha/generate`, `/alpha/whoami`, `/alpha/billing/credits`, `/alpha/billing/subscriptions`, and `/alpha/usage/summary`.
+- The model catalog was refreshed from the `0.26.8` CLI bundle. Existing enabled defaults stay conservative, while additional discovered entries such as Qwen 3.6 Max Preview, MiniMax M2.5, Kimi K2.5, Step 3.5 Flash, Gemini 3.1 Flash Lite, GLM-5, GPT 5.4/5.3 Codex/5.4 Mini, and older Claude variants are present but disabled by default until an operator enables them.
 
 ## Architecture
 
@@ -247,6 +247,8 @@ Project smoke script:
 npm run smoke
 ```
 
+The smoke script reads `.env`, then the installed-service env file at `~/.config/commandcode-bridge/env` on Linux or `/Users/yorha/.config/commandcode-bridge/env` on Yorha's macOS bridge host, then explicit shell variables. Set `BRIDGE_ENV_FILE=/path/to/env` when validating another installed bridge. Explicit shell values such as `BRIDGE_BASE_URL` and `BRIDGE_API_KEY` always win.
+
 If the account is reachable but temporarily blocked by balance/credit, use the routing-only fail-closed smoke mode:
 
 ```bash
@@ -275,7 +277,7 @@ The dashboard is intentionally mobile-first. It is useful from a phone on the sa
 
 - **Header**
   - Shows bridge online/offline state.
-  - Shows bridge version, for example `v0.26.7`.
+  - Shows bridge version, for example `v0.26.8`.
 - **Server Bind**
   - Choose `127.0.0.1` for local-only use.
   - Choose `0.0.0.0` only for LAN/Tailscale/VPN/reverse-proxy use.
@@ -487,7 +489,7 @@ x-api-key: <BRIDGE_API_KEY>
 | `COMMANDCODE_DEFAULT_MODEL`                  | `deepseek/deepseek-v4-pro`   | Model used for `default`.                                                                                                    |
 | `COMMANDCODE_ALLOWED_MODELS`                 | Pro + Flash/catalog defaults | Comma-separated allowlist.                                                                                                   |
 | `COMMANDCODE_ALLOW_UNKNOWN_MODELS`           | `false`                      | Pass arbitrary model IDs upstream. Not recommended.                                                                          |
-| `COMMANDCODE_CLI_VERSION`                    | `0.26.7`                     | Version header sent upstream.                                                                                                |
+| `COMMANDCODE_CLI_VERSION`                    | `0.26.8`                     | Version header sent upstream.                                                                                                |
 | `COMMANDCODE_TIMEOUT_MS`                     | `300000`                     | Upstream request timeout.                                                                                                    |
 | `COMMANDCODE_EMPTY_VISIBLE_RESPONSE_POLICY`  | `error_on_length`            | `error_on_length` fails closed on empty visible `finish_reason: length`; `allow` preserves legacy blank success behavior.    |
 | `REQUEST_BODY_LIMIT_BYTES`                   | `1048576`                    | Fastify body limit.                                                                                                          |

docs/DEPLOYMENT.ko.md

@@ -398,7 +398,7 @@ npm run smoke
 | `COMMANDCODE_DEFAULT_MODEL`        | `deepseek/deepseek-v4-pro`   | `model: "default"` 요청이 실제로 사용할 upstream model입니다.                                                            |
 | `COMMANDCODE_ALLOWED_MODELS`       | Pro + Flash                  | 허용할 model ID 목록입니다. 이 목록 밖 요청은 unknown model 허용 옵션을 켜지 않는 한 거부됩니다.                         |
 | `COMMANDCODE_ALLOW_UNKNOWN_MODELS` | `false`                      | 임의 model ID를 upstream으로 통과시킵니다. 운영에서는 권장하지 않습니다.                                                 |
-| `COMMANDCODE_CLI_VERSION`          | `0.26.7`                     | 테스트된 CommandCode CLI 동작과 맞추기 위해 upstream에 보내는 version header입니다.                                      |
+| `COMMANDCODE_CLI_VERSION`          | `0.26.8`                     | 테스트된 CommandCode CLI 동작과 맞추기 위해 upstream에 보내는 version header입니다.                                      |
 | `COMMANDCODE_TIMEOUT_MS`           | `300000`                     | upstream generation timeout입니다.                                                                                       |
 
 Credential JSON 파일 예시:

docs/DEPLOYMENT.md

@@ -399,7 +399,7 @@ npm run smoke
 | `COMMANDCODE_DEFAULT_MODEL`        | `deepseek/deepseek-v4-pro`   | Upstream model used by `model: "default"`.                                                                               |
 | `COMMANDCODE_ALLOWED_MODELS`       | Pro + Flash                  | Comma-separated allowlist. Requests outside this list are rejected unless unknown models are allowed.                    |
 | `COMMANDCODE_ALLOW_UNKNOWN_MODELS` | `false`                      | Allows arbitrary model IDs to pass through. Not recommended for production.                                              |
-| `COMMANDCODE_CLI_VERSION`          | `0.26.7`                     | Version header sent upstream to match the tested CommandCode CLI behavior.                                               |
+| `COMMANDCODE_CLI_VERSION`          | `0.26.8`                     | Version header sent upstream to match the tested CommandCode CLI behavior.                                               |
 | `COMMANDCODE_TIMEOUT_MS`           | `300000`                     | Upstream generation timeout.                                                                                             |
 
 Credential file shape:

docs/KNOW_HOW.md

@@ -54,7 +54,7 @@ Smoke-test modes:
 
 ## Billing and Multi-Key Routing
 
-CommandCode CLI 0.26.7 `/usage` uses these account endpoints with the same bearer token:
+CommandCode CLI 0.26.8 `/usage` uses these account endpoints with the same bearer token:
 
 - `GET /alpha/whoami` to discover the organization id.
 - `GET /alpha/billing/credits?orgId=...`

docs/PRD.md

@@ -54,7 +54,7 @@ Expose the local CommandCode account's DeepSeek V4 Pro route as a clean, OpenAI-
 
 ## Source Evidence
 
-- Local CommandCode 0.26.7 bundle calls `https://api.commandcode.ai/alpha/generate` and billing/usage endpoints under `/alpha/billing/*` and `/alpha/usage/summary`.
+- Local CommandCode 0.26.8 bundle calls `https://api.commandcode.ai/alpha/generate` and billing/usage endpoints under `/alpha/billing/*` and `/alpha/usage/summary`.
 - Direct Node fetch to `/alpha/whoami` and `/alpha/generate` succeeded.
 - `params.stream=false` is rejected by CommandCode; bridge must always call upstream streaming.
 - Community `pi-commandcode-provider` independently uses the same API path.

install.sh

@@ -382,7 +382,7 @@ fi
   write_env_line COMMANDCODE_DEFAULT_MODEL deepseek/deepseek-v4-pro
   write_env_line COMMANDCODE_ALLOWED_MODELS "$DEFAULT_ALLOWED_MODELS"
   write_env_line COMMANDCODE_ALLOW_UNKNOWN_MODELS false
-  write_env_line COMMANDCODE_CLI_VERSION 0.26.7
+  write_env_line COMMANDCODE_CLI_VERSION 0.26.8
   write_env_line COMMANDCODE_TIMEOUT_MS 300000
   write_env_line COMMANDCODE_EMPTY_VISIBLE_RESPONSE_POLICY error_on_length
   write_env_line COMMANDCODE_BALANCE_ALERT_ENABLED false

package-lock.json

@@ -1,6 +1,6 @@
 {
   "name": "commandcode-bridge",
-  "version": "0.26.7",
+  "version": "0.26.8",
   "description": "OpenAI-compatible HTTP bridge for CommandCode's DeepSeek V4 Pro API path.",
   "type": "module",
   "license": "MIT",